FloVD: Optical Flow Meets Video Diffusion Model for Enhanced Camera-Controlled Video Synthesis
Wonjoon Jin, Qi Dai, Chong Luo, Seung-Hwan Baek, Sunghyun Cho
2025Year
20Top-tier citations
Abstract
Single image Camera parameters … Optical flow maps Figure 1. (Left) Our method using optical flow enables video synthesis with complex camera movements (dolly zoom). (Right) Synthesized video frames with 'zoom-out' camera motion. X-t slice reveals pixel value changes along the red line. Our method shows natural object motion and accurate camera control, while CameraCtrl [9] produces an object without motions, and MotionCtrl [33] produces artifacts.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Cited by top-tier papers20
- Unified Camera Positional Encoding for Controlled Video GenerationCheng Zhang, Boying Li, Meng Wei, Yan-Pei Cao et al.CVPR 2026 · 38 citations
- Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-DistillationSherwin Bahmani, Tianchang Shen, Jiawei Ren, Jiahui Huang et al.ICLR 2026 · 33 citations
- 3D Scene Prompting for Scene-Consistent Camera-Controllable Video GenerationJoungBin Lee, Jaewoo Jung, Jisang Han, Takuya Narihira et al.ICLR 2026 · 14 citations
- Video-As-Prompt: Unified Semantic Control for Video GenerationYuxuan Bian, Xin Chen, Zenan Li, Tiancheng Zhi et al.ICLR 2026 · 13 citations
- WorldStereo: Bridging Camera-Guided Video Generation and Scene Reconstruction via 3D Geometric MemoriesYisu Zhang, Chenjie Cao, Tengfei Wang, Xuhui Zuo et al.CVPR 2026 · 13 citations
Builds on23
- Elucidating the Design Space of Diffusion-Based Generative ModelsTero Karras, Miika Aittala, Timo Aila, Samuli LaineNeurIPS 2022 · 3,959 citations
- Video Diffusion ModelsJonathan Ho, Tim Salimans, Alexey A. Gritsenko, William Chan et al.NeurIPS 2022 · 2,948 citations
- Depth Anything V2Lihe Yang, Bingyi Kang, Zilong Huang, Zhen Zhao et al.NeurIPS 2024 · 2,305 citations
- T2I-Adapter: Learning Adapters to Dig Out More Controllable Ability for Text-to-Image Diffusion ModelsChong Mou, Xintao Wang, Liangbin Xie, Yanze Wu et al.AAAI 2024 · 1,641 citations
- AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific TuningYuwei Guo, Ceyuan Yang, Anyi Rao, Zhengyang Liang et al.ICLR 2024 · 1,493 citations
Related papers
- 3D Cinemagraphy from a Single ImageXingyi Li, Zhiguo Cao, Huiqiang Sun, Jianming Zhang et al.CVPR 2023
- GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera ControlXuanchi Ren, Tianchang Shen, Jiahui Huang, Huan Ling et al.CVPR 2025
- AC3D: Analyzing and Improving 3D Camera Control in Video Diffusion TransformersSherwin Bahmani, Ivan Skorokhodov, Guocheng Qian, Aliaksandr Siarohin et al.CVPR 2025
- MotionCtrl: A Unified and Flexible Motion Controller for Video GenerationZhouxia Wang, Ziyang Yuan, Xintao Wang, Yaowei Li et al.SIGGRAPH 2024 · 123 citations
- ADFactory: An Effective Framework for Generalizing Optical Flow With NeRFHan Ling, Quansen Sun, Yinghui Sun, Xian Xu et al.CVPR 2024
